© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 223165
    Prev
    Next
    INDEX
    Explanations

    unlockables and informal places

    np_acts-logits-general · gemini-2.5-flash-lite

    section beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jeżeli
    0.44
    光源
    0.43
    霧
    0.42
    žení
    0.42
     люди
    0.42
     場
    0.42
    インチ
    0.41
     நிலைய
    0.40
     Gerät
    0.40
    頚
    0.40
    POSITIVE LOGITS
     donc
    0.46
     אבל
    0.46
     thankfully
    0.44
     prossima
    0.44
    쌤
    0.43
     relevancia
    0.43
     metadata
    0.42
     tärke
    0.42
    新闻
    0.42
    долго
    0.42
    Activations Density 0.001%

    No Known Activations